Files in this item



application/pdfSP21-ECE499-Thesis-Erickson, Emma.pdf (712kB)
(no description provided)PDF


Title:Investigating Cold-Start Failure in Active Learning for Images
Author(s):Erickson, Emma
Contributor(s):Do, Minh
Degree:B.S. (bachelor's)
Subject(s):Active Learning
Cold-start Failure
Image Classification
Abstract:Active learning is a machine learning strategy which seeks to achieve the best possible results with the fewest labeled examples. When successful, active learning improves model performance at a lower labeling cost than labeling randomly or uniformly. However, if these active learning strategies are employed too early, active learning may perform worse than random selection, a condition known as cold-start failure. This thesis first characterizes the problem of cold-start failure in image classification, examining the training conditions under which cold-start failure occurs using the MNIST dataset. Following this, behaviors and selections of active learning strategies under cold-start are analyzed and compared to training behavior in both uniform sampling and successful active learning situations. Finally, self-supervision strategies are introduced to generate new features from the images within the unlabeled pool in an attempt to alleviate cold-start failure and allow active learning training to successfully begin earlier. We did not find evidence that this additional feature extraction was useful in alleviating cold-start failure for our dataset.
Issue Date:2021-05
Genre:Dissertation / Thesis
Date Available in IDEALS:2021-08-11

This item appears in the following Collection(s)

Item Statistics